Industrial electrical machine maintenance logs pertinent information, such as fault causality and earlier indications, in the form of a semi-standardized report, previously written and now in digital form. New practices in predictive maintenance, state-of-the-art condition monitoring, include increasing applications of machine learning. Reports contain a large volume of natural text in various languages and semantics, proving costly for feature extraction. This chapter aims to present novel techniques in information extraction to enable literature access to this untapped information reserve. A high level of correlation between text features and fault causality is noted, encouraging research for extended application in the scope of electrical machine maintenance, especially in artificial intelligence indication detection training. Furthermore, these innovative models can be used for decision-making during the repair. Information from well-trained classifiers can be extrapolated to advance fault causality understanding.

Background: The determination of the mechanical properties of biological samples using Atomic Force Microscopy (AFM) at the nanoscale is usually performed using basic models arising from the contact mechanics theory. In particular, the Hertz model is the most frequently used theoretical tool for data processing. However, the Hertz model requires several assumptions such as homogeneous and isotropic samples and indenters with perfectly spherical or conical shapes. As it is widely known, none of these requirements are 100 % fulfilled for the case of indentation experiments at the nanoscale. As a result, significant errors arise in the Young’s modulus calculation. At the same time, an analytical model that could account complexities of soft biomaterials, such as nonlinear behavior, anisotropy, and heterogeneity, may be far-reaching. In addition, this hypothetical model would be ‘too difficult’ to be applied in real clinical activities since it would require very heavy workload and highly specialized personnel. Objective: In this paper a simple solution is provided to the aforementioned dead-end. A new approach is introduced in order to provide a simple and accurate method for the mechanical characterization at the nanoscale. Method: The ratio of the work done by the indenter on the sample of interest to the work done by the indenter on a reference sample is introduced as a new physical quantity that does not require homogeneous, isotropic samples or perfect indenters. Results: The proposed approach, not only provides an accurate solution from a physical perspective but also a simpler solution which does not require activities such as the determination of the cantilever’s spring constant and the dimensions of the AFM tip. Conclusion: The proposed, by this opinion paper, solution aims to provide a significant opportunity to overcome the existing limitations provided by Hertzian mechanics and apply AFM techniques in real clinical activities.